Papers
1
Total Citations
1
H-Index
1
About
Fazeng Li is a rising researcher in computer vision and deep learning, whose work centers on advancing geometric perception and semantic correspondence—a foundational task for applications like style transfer, robot manipulation, and pose estimation. Li’s key contribution is the development of a Depth Awareness and Learnable Feature Fusion Network, which enhances the ability of models to perceive geometry by integrating depth cues with learnable feature fusion mechanisms. This innovation addresses a critical challenge in multi-sensor data fusion, where deep learning is now the dominant paradigm. Although their most-cited paper, published in 2024, has garnered 1 citation to date, it represents a promising step toward more robust semantic correspondence in complex visual environments. Li’s focus on bridging depth awareness with feature learning positions them at the intersection of geometric deep learning and practical robotics, with potential to impact real-world systems requiring precise spatial understanding. As their research evolves, Li is poised to contribute significantly to the growing field of perception-driven AI.
Research Focus
Key Achievements
Top Papers
- 1